AdaptiveLayerLoss(model=model,

f0c76d4 verified over 1 year ago

25.2 kB

metadata

language:
  - en
library_name: sentence-transformers
tags:
  - sentence-transformers
  - sentence-similarity
  - feature-extraction
  - generated_from_trainer
  - dataset_size:67190
  - loss:AdaptiveLayerLoss
  - loss:MultipleNegativesRankingLoss
base_model: microsoft/deberta-v3-small
datasets:
  - stanfordnlp/snli
metrics:
  - cosine_accuracy
  - cosine_accuracy_threshold
  - cosine_f1
  - cosine_f1_threshold
  - cosine_precision
  - cosine_recall
  - cosine_ap
  - dot_accuracy
  - dot_accuracy_threshold
  - dot_f1
  - dot_f1_threshold
  - dot_precision
  - dot_recall
  - dot_ap
  - manhattan_accuracy
  - manhattan_accuracy_threshold
  - manhattan_f1
  - manhattan_f1_threshold
  - manhattan_precision
  - manhattan_recall
  - manhattan_ap
  - euclidean_accuracy
  - euclidean_accuracy_threshold
  - euclidean_f1
  - euclidean_f1_threshold
  - euclidean_precision
  - euclidean_recall
  - euclidean_ap
  - max_accuracy
  - max_accuracy_threshold
  - max_f1
  - max_f1_threshold
  - max_precision
  - max_recall
  - max_ap
  - pearson_cosine
  - spearman_cosine
  - pearson_manhattan
  - spearman_manhattan
  - pearson_euclidean
  - spearman_euclidean
  - pearson_dot
  - spearman_dot
  - pearson_max
  - spearman_max
widget:
  - source_sentence: A worker peers out from atop a building under construction.
    sentences:
      - The man pleads for mercy.
      - People and a baby crossing the street.
      - A person is atop of a building.
  - source_sentence: >-
      An aisle at Best Buy with an employee standing at the computer and a Geek
      Squad sign in the background.
    sentences:
      - the man is watching the stars
      - The employee is wearing a blue shirt.
      - A person balancing.
  - source_sentence: >-
      A man with a long white beard is examining a camera and another man with a
      black shirt is in the background.
    sentences:
      - a man is with another man
      - Children in uniforms climb a tower.
      - There are five children.
  - source_sentence: A black dog with a blue collar is jumping into the water.
    sentences:
      - The dog is playing tug of war with a stick.
      - There is a woman painting.
      - A black dog wearing a blue collar is chasing something into the water.
  - source_sentence: A wet child stands in chest deep ocean water.
    sentences:
      - A woman paints a portrait of her best friend.
      - A person in red is cutting the grass on a riding mower
      - The child s playing on the beach.
pipeline_tag: sentence-similarity
model-index:
  - name: SentenceTransformer based on microsoft/deberta-v3-small
    results:
      - task:
          type: binary-classification
          name: Binary Classification
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: cosine_accuracy
            value: 0.6583157259281618
            name: Cosine Accuracy
          - type: cosine_accuracy_threshold
            value: 0.6766541004180908
            name: Cosine Accuracy Threshold
          - type: cosine_f1
            value: 0.7049362860324137
            name: Cosine F1
          - type: cosine_f1_threshold
            value: 0.6017583012580872
            name: Cosine F1 Threshold
          - type: cosine_precision
            value: 0.6115046147241897
            name: Cosine Precision
          - type: cosine_recall
            value: 0.8320677570093458
            name: Cosine Recall
          - type: cosine_ap
            value: 0.6995030811464378
            name: Cosine Ap
          - type: dot_accuracy
            value: 0.6272260790824027
            name: Dot Accuracy
          - type: dot_accuracy_threshold
            value: 163.25054931640625
            name: Dot Accuracy Threshold
          - type: dot_f1
            value: 0.6976381461675579
            name: Dot F1
          - type: dot_f1_threshold
            value: 119.20779418945312
            name: Dot F1 Threshold
          - type: dot_precision
            value: 0.5639409221902018
            name: Dot Precision
          - type: dot_recall
            value: 0.914427570093458
            name: Dot Recall
          - type: dot_ap
            value: 0.643747511442345
            name: Dot Ap
          - type: manhattan_accuracy
            value: 0.6571083610021129
            name: Manhattan Accuracy
          - type: manhattan_accuracy_threshold
            value: 243.75453186035156
            name: Manhattan Accuracy Threshold
          - type: manhattan_f1
            value: 0.7055783910745744
            name: Manhattan F1
          - type: manhattan_f1_threshold
            value: 295.95947265625
            name: Manhattan F1 Threshold
          - type: manhattan_precision
            value: 0.5900608917697898
            name: Manhattan Precision
          - type: manhattan_recall
            value: 0.8773364485981309
            name: Manhattan Recall
          - type: manhattan_ap
            value: 0.7072033306346501
            name: Manhattan Ap
          - type: euclidean_accuracy
            value: 0.6590703290069424
            name: Euclidean Accuracy
          - type: euclidean_accuracy_threshold
            value: 12.141830444335938
            name: Euclidean Accuracy Threshold
          - type: euclidean_f1
            value: 0.7036813518406759
            name: Euclidean F1
          - type: euclidean_f1_threshold
            value: 14.197540283203125
            name: Euclidean F1 Threshold
          - type: euclidean_precision
            value: 0.5996708496194199
            name: Euclidean Precision
          - type: euclidean_recall
            value: 0.8513434579439252
            name: Euclidean Recall
          - type: euclidean_ap
            value: 0.7035256676322055
            name: Euclidean Ap
          - type: max_accuracy
            value: 0.6590703290069424
            name: Max Accuracy
          - type: max_accuracy_threshold
            value: 243.75453186035156
            name: Max Accuracy Threshold
          - type: max_f1
            value: 0.7055783910745744
            name: Max F1
          - type: max_f1_threshold
            value: 295.95947265625
            name: Max F1 Threshold
          - type: max_precision
            value: 0.6115046147241897
            name: Max Precision
          - type: max_recall
            value: 0.914427570093458
            name: Max Recall
          - type: max_ap
            value: 0.7072033306346501
            name: Max Ap
      - task:
          type: semantic-similarity
          name: Semantic Similarity
        dataset:
          name: Unknown
          type: unknown
        metrics:
          - type: pearson_cosine
            value: 0.732169941341086
            name: Pearson Cosine
          - type: spearman_cosine
            value: 0.7344587206087978
            name: Spearman Cosine
          - type: pearson_manhattan
            value: 0.7537099624360986
            name: Pearson Manhattan
          - type: spearman_manhattan
            value: 0.7550555196955944
            name: Spearman Manhattan
          - type: pearson_euclidean
            value: 0.7468210439584286
            name: Pearson Euclidean
          - type: spearman_euclidean
            value: 0.74849026008206
            name: Spearman Euclidean
          - type: pearson_dot
            value: 0.6142835401925993
            name: Pearson Dot
          - type: spearman_dot
            value: 0.6100201108417316
            name: Spearman Dot
          - type: pearson_max
            value: 0.7537099624360986
            name: Pearson Max
          - type: spearman_max
            value: 0.7550555196955944
            name: Spearman Max

SentenceTransformer based on microsoft/deberta-v3-small

This is a sentence-transformers model finetuned from microsoft/deberta-v3-small on the stanfordnlp/snli dataset. It maps sentences & paragraphs to a 768-dimensional dense vector space and can be used for semantic textual similarity, semantic search, paraphrase mining, text classification, clustering, and more.

Model Details

Model Description

Model Type: Sentence Transformer
Base model: microsoft/deberta-v3-small
Maximum Sequence Length: 512 tokens
Output Dimensionality: 768 tokens
Similarity Function: Cosine Similarity
Training Dataset:
- stanfordnlp/snli
Language: en

Model Sources

Documentation: Sentence Transformers Documentation
Repository: Sentence Transformers on GitHub
Hugging Face: Sentence Transformers on Hugging Face

Full Model Architecture

SentenceTransformer(
  (0): Transformer({'max_seq_length': 512, 'do_lower_case': False}) with Transformer model: DebertaV2Model 
  (1): Pooling({'word_embedding_dimension': 768, 'pooling_mode_cls_token': False, 'pooling_mode_mean_tokens': True, 'pooling_mode_max_tokens': False, 'pooling_mode_mean_sqrt_len_tokens': False, 'pooling_mode_weightedmean_tokens': False, 'pooling_mode_lasttoken': False, 'include_prompt': True})
)

Usage

Direct Usage (Sentence Transformers)

First install the Sentence Transformers library:

pip install -U sentence-transformers

Then you can load this model and run inference.

from sentence_transformers import SentenceTransformer

# Download from the 🤗 Hub
model = SentenceTransformer("bobox/DeBERTaV3-small-ST-AdaptiveLayers-ep2")
# Run inference
sentences = [
    'A wet child stands in chest deep ocean water.',
    'The child s playing on the beach.',
    'A woman paints a portrait of her best friend.',
]
embeddings = model.encode(sentences)
print(embeddings.shape)
# [3, 768]

# Get the similarity scores for the embeddings
similarities = model.similarity(embeddings, embeddings)
print(similarities.shape)
# [3, 3]

Evaluation

Metrics

Binary Classification

Evaluated with BinaryClassificationEvaluator

Metric	Value
cosine_accuracy	0.6583
cosine_accuracy_threshold	0.6767
cosine_f1	0.7049
cosine_f1_threshold	0.6018
cosine_precision	0.6115
cosine_recall	0.8321
cosine_ap	0.6995
dot_accuracy	0.6272
dot_accuracy_threshold	163.2505
dot_f1	0.6976
dot_f1_threshold	119.2078
dot_precision	0.5639
dot_recall	0.9144
dot_ap	0.6437
manhattan_accuracy	0.6571
manhattan_accuracy_threshold	243.7545
manhattan_f1	0.7056
manhattan_f1_threshold	295.9595
manhattan_precision	0.5901
manhattan_recall	0.8773
manhattan_ap	0.7072
euclidean_accuracy	0.6591
euclidean_accuracy_threshold	12.1418
euclidean_f1	0.7037
euclidean_f1_threshold	14.1975
euclidean_precision	0.5997
euclidean_recall	0.8513
euclidean_ap	0.7035
max_accuracy	0.6591
max_accuracy_threshold	243.7545
max_f1	0.7056
max_f1_threshold	295.9595
max_precision	0.6115
max_recall	0.9144
max_ap	0.7072

Semantic Similarity

Evaluated with EmbeddingSimilarityEvaluator

Metric	Value
pearson_cosine	0.7322
spearman_cosine	0.7345
pearson_manhattan	0.7537
spearman_manhattan	0.7551
pearson_euclidean	0.7468
spearman_euclidean	0.7485
pearson_dot	0.6143
spearman_dot	0.61
pearson_max	0.7537
spearman_max	0.7551

Training Details

Training Dataset

stanfordnlp/snli

Dataset: stanfordnlp/snli at cdb5c3d
Size: 67,190 training samples
Columns: sentence1, sentence2, and label
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 label
type string string int
details
min: 4 tokens
mean: 21.19 tokens
max: 133 tokens

min: 4 tokens
mean: 11.77 tokens
max: 49 tokens

0: 100.00%

	sentence1	sentence2	label
type	string	string	int
details	min: 4 tokens mean: 21.19 tokens max: 133 tokens	min: 4 tokens mean: 11.77 tokens max: 49 tokens	0: 100.00%

Samples:

sentence1	sentence2	label
`Without a placebo group, we still won't know if any of the treatments are better than nothing and therefore worth giving.`	`It is necessary to use a controlled method to ensure the treatments are worthwhile.`	`0`
`It was conducted in silence.`	`It was done silently.`	`0`
`oh Lewisville any decent food in your cafeteria up there`	`Is there any decent food in your cafeteria up there in Lewisville?`	`0`

Loss: AdaptiveLayerLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "n_layers_per_step": 1,
    "last_layer_weight": 1,
    "prior_layers_weight": 1,
    "kl_div_weight": 1,
    "kl_temperature": 1
}

Evaluation Dataset

stanfordnlp/snli

Dataset: stanfordnlp/snli at cdb5c3d
Size: 1,500 evaluation samples
Columns: sentence1, sentence2, and score
Approximate statistics based on the first 1000 samples:
sentence1 sentence2 score
type string string float
details
min: 5 tokens
mean: 14.77 tokens
max: 45 tokens

min: 6 tokens
mean: 14.74 tokens
max: 49 tokens

min: 0.0
mean: 0.47
max: 1.0

	sentence1	sentence2	score
type	string	string	float
details	min: 5 tokens mean: 14.77 tokens max: 45 tokens	min: 6 tokens mean: 14.74 tokens max: 49 tokens	min: 0.0 mean: 0.47 max: 1.0

Samples:

sentence1	sentence2	score
`A man with a hard hat is dancing.`	`A man wearing a hard hat is dancing.`	`1.0`
`A young child is riding a horse.`	`A child is riding a horse.`	`0.95`
`A man is feeding a mouse to a snake.`	`The man is feeding a mouse to the snake.`	`1.0`

Loss: AdaptiveLayerLoss with these parameters:

{
    "loss": "MultipleNegativesRankingLoss",
    "n_layers_per_step": 1,
    "last_layer_weight": 1,
    "prior_layers_weight": 1,
    "kl_div_weight": 1,
    "kl_temperature": 1
}

Training Hyperparameters

Non-Default Hyperparameters

eval_strategy: steps
per_device_train_batch_size: 42
per_device_eval_batch_size: 22
learning_rate: 3e-06
weight_decay: 1e-08
num_train_epochs: 2
lr_scheduler_type: cosine
warmup_ratio: 0.5
save_safetensors: False
fp16: True
hub_model_id: bobox/DeBERTaV3-small-ST-AdaptiveLayers-ep2-tmp
hub_strategy: checkpoint
hub_private_repo: True
batch_sampler: no_duplicates

All Hyperparameters

Click to expand

overwrite_output_dir: False
do_predict: False
eval_strategy: steps
prediction_loss_only: True
per_device_train_batch_size: 42
per_device_eval_batch_size: 22
per_gpu_train_batch_size: None
per_gpu_eval_batch_size: None
gradient_accumulation_steps: 1
eval_accumulation_steps: None
learning_rate: 3e-06
weight_decay: 1e-08
adam_beta1: 0.9
adam_beta2: 0.999
adam_epsilon: 1e-08
max_grad_norm: 1.0
num_train_epochs: 2
max_steps: -1
lr_scheduler_type: cosine
lr_scheduler_kwargs: {}
warmup_ratio: 0.5
warmup_steps: 0
log_level: passive
log_level_replica: warning
log_on_each_node: True
logging_nan_inf_filter: True
save_safetensors: False
save_on_each_node: False
save_only_model: False
restore_callback_states_from_checkpoint: False
no_cuda: False
use_cpu: False
use_mps_device: False
seed: 42
data_seed: None
jit_mode_eval: False
use_ipex: False
bf16: False
fp16: True
fp16_opt_level: O1
half_precision_backend: auto
bf16_full_eval: False
fp16_full_eval: False
tf32: None
local_rank: 0
ddp_backend: None
tpu_num_cores: None
tpu_metrics_debug: False
debug: []
dataloader_drop_last: False
dataloader_num_workers: 0
dataloader_prefetch_factor: None
past_index: -1
disable_tqdm: False
remove_unused_columns: True
label_names: None
load_best_model_at_end: False
ignore_data_skip: False
fsdp: []
fsdp_min_num_params: 0
fsdp_config: {'min_num_params': 0, 'xla': False, 'xla_fsdp_v2': False, 'xla_fsdp_grad_ckpt': False}
fsdp_transformer_layer_cls_to_wrap: None
accelerator_config: {'split_batches': False, 'dispatch_batches': None, 'even_batches': True, 'use_seedable_sampler': True, 'non_blocking': False, 'gradient_accumulation_kwargs': None}
deepspeed: None
label_smoothing_factor: 0.0
optim: adamw_torch
optim_args: None
adafactor: False
group_by_length: False
length_column_name: length
ddp_find_unused_parameters: None
ddp_bucket_cap_mb: None
ddp_broadcast_buffers: False
dataloader_pin_memory: True
dataloader_persistent_workers: False
skip_memory_metrics: True
use_legacy_prediction_loop: False
push_to_hub: False
resume_from_checkpoint: None
hub_model_id: bobox/DeBERTaV3-small-ST-AdaptiveLayers-ep2-tmp
hub_strategy: checkpoint
hub_private_repo: True
hub_always_push: False
gradient_checkpointing: False
gradient_checkpointing_kwargs: None
include_inputs_for_metrics: False
eval_do_concat_batches: True
fp16_backend: auto
push_to_hub_model_id: None
push_to_hub_organization: None
mp_parameters:
auto_find_batch_size: False
full_determinism: False
torchdynamo: None
ray_scope: last
ddp_timeout: 1800
torch_compile: False
torch_compile_backend: None
torch_compile_mode: None
dispatch_batches: None
split_batches: None
include_tokens_per_second: False
include_num_input_tokens_seen: False
neftune_noise_alpha: None
optim_target_modules: None
batch_eval_metrics: False
batch_sampler: no_duplicates
multi_dataset_batch_sampler: proportional

Training Logs

Epoch	Step	Training Loss	loss	max_ap	spearman_cosine
0.1	160	4.6003	4.8299	0.6017	-
0.2	320	4.0659	4.3436	0.6168	-
0.3	480	3.4886	4.0840	0.6339	-
0.4	640	3.0592	3.6422	0.6611	-
0.5	800	2.5728	3.1927	0.6773	-
0.6	960	2.184	2.8322	0.6893	-
0.7	1120	1.8744	2.4892	0.6954	-
0.8	1280	1.757	2.4453	0.7002	-
0.9	1440	1.5872	2.2565	0.7010	-
1.0	1600	1.446	2.1391	0.7046	-
1.1	1760	1.3892	2.1236	0.7058	-
1.2	1920	1.2567	1.9738	0.7053	-
1.3	2080	1.2233	1.8925	0.7063	-
1.4	2240	1.1954	1.8392	0.7075	-
1.5	2400	1.1395	1.9081	0.7065	-
1.6	2560	1.1211	1.8080	0.7074	-
1.7	2720	1.0825	1.8408	0.7073	-
1.8	2880	1.1358	1.7363	0.7073	-
1.9	3040	1.0628	1.8936	0.7072	-
2.0	3200	1.1412	1.7846	0.7072	-
None	0	-	3.0121	0.7072	0.7345

Framework Versions

Python: 3.10.13
Sentence Transformers: 3.0.1
Transformers: 4.41.2
PyTorch: 2.1.2
Accelerate: 0.30.1
Datasets: 2.19.2
Tokenizers: 0.19.1

Citation

BibTeX

Sentence Transformers

@inproceedings{reimers-2019-sentence-bert,
    title = "Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks",
    author = "Reimers, Nils and Gurevych, Iryna",
    booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing",
    month = "11",
    year = "2019",
    publisher = "Association for Computational Linguistics",
    url = "https://arxiv.org/abs/1908.10084",
}

AdaptiveLayerLoss

@misc{li20242d,
    title={2D Matryoshka Sentence Embeddings}, 
    author={Xianming Li and Zongxi Li and Jing Li and Haoran Xie and Qing Li},
    year={2024},
    eprint={2402.14776},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}

MultipleNegativesRankingLoss

@misc{henderson2017efficient,
    title={Efficient Natural Language Response Suggestion for Smart Reply}, 
    author={Matthew Henderson and Rami Al-Rfou and Brian Strope and Yun-hsuan Sung and Laszlo Lukacs and Ruiqi Guo and Sanjiv Kumar and Balint Miklos and Ray Kurzweil},
    year={2017},
    eprint={1705.00652},
    archivePrefix={arXiv},
    primaryClass={cs.CL}
}